{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.20911", "kind": "paper", "url": "https://arxiv.org/abs/2607.20911"}, {"id": "gh:tencent/workbuddy-bench", "kind": "repo", "url": "https://github.com/Tencent/workbuddy-bench"}, {"id": "hf:tencent/workbuddy-bench", "kind": "dataset", "url": "https://huggingface.co/datasets/tencent/workbuddy-bench"}, {"kind": "website", "url": "https://workbuddybench.com/"}], "authors": ["Tencent WorkBuddy Bench Team", "Siqi Cai", "Shaopeng Chen", "Xiang Fei", "Yong Mao", "Zihan Xu", "Zhiheng Lyu", "Zhijian Shao", "Yuchen Shi", "Shuwen Zhang", "Chaofan Qiu", "Linjie Che", "Xiaoxi Zhao", "Feng Wu", "Kai Zhang", "Chaofan Zhu", "Yubin Qi", "Xiaoyun Liang", "Peijie Dong", "Yunhao Zhang", "Yuanjie Zhu", "Ling Jiang", "Xianjun Zhang", "Zhehang Chu", "Anyuan Sang", "Zhen Feng", "Sen Nie", "Shi Wu", "Yuanzhen Xu", "Xin Li", "Ning Yang", "Zhiqiang Dong", "Hande Dong", "Qiang Lin", "Yi Liu", "Yunsheng Wu", "Ke Li", "Xing Sun"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.20911", "source_url": "https://arxiv.org/abs/2607.20911"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "Multi-domain coding-agent benchmark with reverse-engineered tasks across Code, Web, Office, and Security. Each subset has its own scoring instrument; scores are not comparable across subsets."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.20911", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.20911", "title": "Tencent WorkBuddy Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.20911", "modality": null, "name": "Tencent WorkBuddy Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_tencent-workbuddy-bench_93d020ca", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b6261cfc9ee18732cbba5623b0401547c44bab0604e2f3678ac8444a78e5a1ee", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.20911"}, "publisher": null, "released": "2026-07-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.20911", "source_url": "https://arxiv.org/abs/2607.20911"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-20911", "source": "claire_radar", "source_benchmark_id": "2607.20911", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Tencent/workbuddy-bench", "githubScope": "benchmark_repo", "githubStars": 374, "hfDailySubmittedAt": "2026-07-24T00:00:00.000Z", "hfDataset": "tencent/workbuddy-bench", "hfDatasetDownloads": 1977, "hfDatasetLikes": 19, "hfPaperUpvotes": 24, "hfPaperUrl": "https://huggingface.co/papers/2607.20911", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetLikes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "e21fc569d4441078bda1a7ed61d71fc381a4d6b6c9af3cc933eb570a1f43a7f1", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Multi-domain coding-agent benchmark with reverse-engineered tasks across Code, Web, Office, and Security. Each subset has its own scoring instrument; scores are not comparable across subsets.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model leaderboard."}, "familyId": "bmf_c8a034f326c0", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/Tencent/workbuddy-bench", "url": "https://github.com/Tencent/workbuddy-bench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Tencent/workbuddy-bench", "url": "https://huggingface.co/papers/2607.20911"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Tencent/workbuddy-bench", "url": "https://arxiv.org/abs/2607.20911"}], "scope": "benchmark_repo", "url": "https://github.com/Tencent/workbuddy-bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_tencent-workbuddy-bench_93d020ca", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/Tencent/workbuddy-bench", "data": "https://huggingface.co/datasets/tencent/workbuddy-bench", "hfPaper": "https://huggingface.co/papers/2607.20911", "paper": "https://arxiv.org/abs/2607.20911", "pdf": "https://arxiv.org/pdf/2607.20911", "project": "https://workbuddybench.com/", "report": "https://arxiv.org/abs/2607.20911"}, "metrics": [], "motivation": "We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model leaderboard.", "name": "Tencent WorkBuddy Bench", "oneLine": "Multi-domain coding-agent benchmark with reverse-engineered tasks across Code, Web, Office, and Security. Each subset has its own scoring instrument; scores are not comparable across subsets.", "paperTitle": "Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.20911", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "High", "coverage": 1.0, "datasetDownloadRank": 8, "datasetRankPopulation": 85, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.7911380813270456, "value": 374}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.7816012936222202, "value": 1977}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.5687580068552543, "value": 24}}, "confidence": "High", "coverage": 1.0, "rank": 4, "score": 75}, "method": "attention-ranking-v13", "rank": 4, "score": 75}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-23", "source": {"authors": ["Tencent WorkBuddy Bench Team: Siqi Cai", "Shaopeng Chen", "Xiang Fei", "Yong Mao", "Zihan Xu", "Zhiheng Lyu", "Zhijian Shao", "Yuchen Shi", "Shuwen Zhang", "Chaofan Qiu", "Linjie Che", "Xiaoxi Zhao", "Feng Wu", "Kai Zhang", "Chaofan Zhu", "Yubin Qi", "Xiaoyun Liang", "Peijie Dong", "Yunhao Zhang", "Yuanjie Zhu", "Ling Jiang", "Xianjun Zhang", "Zhehang Chu", "Anyuan Sang", "Zhen Feng", "Sen Nie", "Shi Wu", "Yuanzhen Xu", "Xin Li", "Ning Yang", "Zhiqiang Dong", "Hande Dong", "Qiang Lin", "Yi Liu", "Yunsheng Wu", "Ke Li and Xing Sun"], "categories": ["cs.CL", "cs.SE"], "id": "2607.20911", "title": "Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction", "type": "arxiv", "url": "https://arxiv.org/abs/2607.20911"}, "sourceUpdatedAt": "2026-07-23T04:34:06Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Addresses contamination in coding-agent evaluation by constructing tasks not discoverable via web search, and provides a reproducible open-source framework for auditable third-party runs."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
